Predicting MCI-to-Alzheimer’s Conversion: A Systematic Benchmark of Classical, Machine Learning, and Deep Survival Models

Background/Objectives: Predicting time-to-conversion from mild cognitive impairment (MCI) to Alzheimer’s disease (AD) is a critical clinical challenge. Most survival analyses rely on static baseline variables, ignoring the temporal dynamics of serial neuroimaging. We benchmark seven survival model families using a novel temporal MRI descriptor pipeline on ADNI. Methods: A cohort of 661 MCI patients (250 conversion events, 37.8%, median follow-up 42.0 months) was constructed from ADNI. FreeSurfer volumetrics of six brain regions were summarised into three time-based descriptors each (atrophy rate, trajectory variability σ, and time-weighted cumulative mean μ) under strict anti-leakage constraints, yielding 18 neuroimaging features which, combined with six clinical variables (age, sex, education, MMSE, ADAS-13, and APOE-ε4), form a 24-dimensional covariate vector. Cox PH, Weibull AFT, Exponential, RSF, GBST, DeepSurv, and DeepHit were evaluated under stratified 5-fold cross-validation and assessed on an independent OASIS-3 cohort (n=78) as an exploratory analysis. Results: All seven models achieved C-index 0.853–0.863 (Δ=0.010), with Cox PH reaching 0.863±0.027 using only routine structural MRI. Time-dependent AUC ranged from 0.856 (12 months) to 0.938 (48 months). Risk stratification by quartile yielded highly separated Kaplan-Meier curves (log-rank p<0.001). On OASIS-3 (n=78, exploratory), classical models showed preliminary cross-cohort consistency (Weibull AFT 0.760±0.063, RSF 0.759±0.049), while deep learning degraded substantially (DeepSurv 0.551±0.116); these results are hypothesis-generating and should not be interpreted as confirmatory given the small per-fold sample size (EPV ≈ 1). Conclusions: The temporal MRI descriptor pipeline achieves a C-index of 0.863 using only routine structural MRI, without PET or CSF biomarkers, demonstrating strong discriminative performance on ADNI MCI-to-AD conversion. The narrow performance band (Δ=0.010) suggests that, within this feature-engineering paradigm, no clear performance separation was observed among the evaluated model architectures; this convergence may reflect feature-level rather than architecture-level constraints, although the underlying cause cannot be established from discriminative performance alone. Classical models showed more stable cross-cohort behaviour under data-scarce conditions; prospective validation on larger cohorts with full covariate parity is required before clinical translation can be considered.